© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42050
    Prev
    Next
    INDEX
    Explanations

    words that signify destruction or demolition actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.05
    3:0.05
    4:0.13
    5:0.03
    6:0.03
    7:0.37
    8:0.02
    9:0.04
    10:0.13
    11:0.06
    Negative Logits
    rared
    -1.72
    podcast
    -1.67
    OA
    -1.66
    verbal
    -1.65
    IRED
    -1.58
    DIT
    -1.57
     Niño
    -1.57
    ñ
    -1.55
    yip
    -1.49
    intent
    -1.48
    POSITIVE LOGITS
     barracks
    1.87
     castles
    1.83
     ceilings
    1.83
     demolished
    1.79
     dismantled
    1.78
     premises
    1.77
     temples
    1.76
     houses
    1.68
     towers
    1.67
     apartments
    1.66
    Activations Density 0.004%

    No Known Activations